© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 53954
    Prev
    Next
    INDEX
    Explanations

    css file paths

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on literal file‐extension tokens (especially .scss, .css, and .html) when code is referencing stylesheet or template file paths.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -1.29
    ctober
    -1.20
     acidente
    -1.16
     Its
    -1.13
     condomínio
    -1.11
    ofag
    -1.09
     人民
    -1.09
     either
    -1.09
     Japão
    -1.09
    ;%%
    -1.08
    POSITIVE LOGITS
    <0xA3>
    1.24
    Kamen
    1.20
    Berat
    1.19
    ポイントは
    1.19
    ってこと
    1.19
    伟大
    1.16
    Nemo
    1.12
     проблему
    1.10
     diputado
    1.10
    時間は
    1.09
    Activations Density 0.001%

    No Known Activations